diff mbox series

[PULL,15/34] migration/multifd: Forbid spurious wakeups

Message ID 20240208030528.368214-16-peterx@redhat.com
State New
Headers show
Series [PULL,01/34] migration: prevent migration when VM has poisoned memory | expand

Commit Message

Peter Xu Feb. 8, 2024, 3:05 a.m. UTC 
From: Peter Xu <peterx@redhat.com>

Now multifd's logic is designed to have no spurious wakeup.  I still
remember a talk to Juan and he seems to agree we should drop it now, and if
my memory was right it was there because multifd used to hit that when
still debugging.

Let's drop it and see what can explode; as long as it's not reaching
soft-freeze.

Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240202102857.110210-15-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 migration/multifd.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/migration/multifd.c b/migration/multifd.c
index 6aa44340de..28b54100cd 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -756,7 +756,9 @@  static void *multifd_send_thread(void *opaque)
             p->next_packet_size = 0;
             qatomic_set(&p->pending_job, false);
             qemu_mutex_unlock(&p->mutex);
-        } else if (qatomic_read(&p->pending_sync)) {
+        } else {
+            /* If not a normal job, must be a sync request */
+            assert(qatomic_read(&p->pending_sync));
             p->flags = MULTIFD_FLAG_SYNC;
             multifd_send_fill_packet(p);
             ret = qio_channel_write_all(p->c, (void *)p->packet,
@@ -771,9 +773,6 @@  static void *multifd_send_thread(void *opaque)
             qatomic_set(&p->pending_sync, false);
             qemu_mutex_unlock(&p->mutex);
             qemu_sem_post(&p->sem_sync);
-        } else {
-            qemu_mutex_unlock(&p->mutex);
-            /* sometimes there are spurious wakeups */
         }
     }